Research map / 3D vision / Human pose estimation
IMU-HOI: A Symbiotic Framework for Coherent Human-Object Interaction and Motion Capture via Contact-Conscious Inertial Fusion
Lizhou Lin, Songpengcheng Xia, Zengyuan Lai, Lan Sun, Jiarui Yang, Ling Pei
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add FK branch to IMU-only object head (contact-gated fusion) (ablation) | IMU-HOI · IMHD2 | Obj Err (cm): 68.59 -> 43.97 | Improved |
| add IMU branch to FK-only object head (ablation) | IMU-HOI · IMHD2 | Obj Err (cm): 61.58 -> 43.97 | Improved |
| add FK branch to IMU-only object head (ablation) | IMU-HOI · OMOMO | Obj Err (cm): 11.52 -> 11.31 | Improved |
| add FK branch to IMU-only object head (ablation) | IMU-HOI · OMOMO | HOI Err (cm): 18.07 -> 17.44 | Improved |
| add IMU branch to FK-only object head (ablation) | IMU-HOI · BEHAVE | HOI Err (cm): 24.58 -> 25.74 | Hurt |
| add FK branch to IMU-only object head (ablation) | IMU-HOI · BEHAVE | Obj Err (cm): 22.99 -> 20.90 | Improved |
| plug contact-gated fusion into GlobalPose backbone | GlobalPose* · IMHD2 | Obj Err (cm): 101.27 -> 46.70 | Improved |
| plug contact-gated fusion into GlobalPose backbone | GlobalPose* · IMHD2 | HOI Err (cm): 102.03 -> 53.69 | Improved |
| plug contact-gated fusion into DIP backbone | DIP* · OMOMO | Obj Err (cm): 25.84 -> 13.95 | Improved |
| plug contact-gated fusion into TransPose backbone | TransPose* · OMOMO | HOI Err (cm): 32.73 -> 29.52 | Improved |
| IMU-HOI versus GlobalPose* on root translation | IMU-HOI · IMHD2 | Trans Err (cm): 58.36 -> 18.37 | Improved |
| IMU-HOI versus GlobalPose* on root translation | IMU-HOI · OMOMO | Trans Err (cm): 10.80 -> 11.07 | No clear effect |
Closest papers by meaning
- I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions (CVPR 2024 · similarity 0.93)
- InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation (CVPR 2025 · similarity 0.88)
- InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions (CVPR 2025 · similarity 0.87)
- CG-HOI: Contact-Guided 3D Human-Object Interaction Generation (CVPR 2024 · similarity 0.87)
- Real2Sim in HOI: Toward Physically Plausible HOI Reconstruction from Monocular Videos (NeurIPS 2026 · similarity 0.86)
- MotionPRO: Exploring the Role of Pressure in Human MoCap and Beyond (CVPR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
